Learning augmented memory joint aberrance repressed correlation filters for visual tracking
With its outstanding performance and tracking speed, discriminative correlation filters (DCF) have gained much attention in visual object tracking, where time-consuming correlation operations can be efficiently computed utilizing the discrete Fourier transform (DFT) with symmetric properties. Nevert...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI
2022
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/40157/1/Learning%20augmented%20memory%20joint%20aberrance%20repressed%20correlation.pdf |
| _version_ | 1796996194420916224 |
|---|---|
| author | Ji, Yuanfa He, Jianzhong Sun, Xiyan Bai, Yang Wei, Zhaochuan Kamarul Hawari, Ghazali |
| author_facet | Ji, Yuanfa He, Jianzhong Sun, Xiyan Bai, Yang Wei, Zhaochuan Kamarul Hawari, Ghazali |
| author_sort | Ji, Yuanfa |
| collection | UMP |
| description | With its outstanding performance and tracking speed, discriminative correlation filters (DCF) have gained much attention in visual object tracking, where time-consuming correlation operations can be efficiently computed utilizing the discrete Fourier transform (DFT) with symmetric properties. Nevertheless, the inherent issues of boundary effects and filter degradation, as well as occlusion and background clutter, degrade the tracking performance. In this work, we proposed an augmented memory joint aberrance repressed correlation filter (AMRCF) for visual tracking. Based on the background-aware correlation filter (BACF), we introduced adaptive spatial regularity to mitigate the boundary effect. Several historical views and the current view are exploited to train the model together as a way to reinforce the memory. Furthermore, aberrance repression regularization was introduced to suppress response anomalies due to occlusion and deformation, while adopting the dynamic updating strategy to reduce the impact of anomalies on the appearance model. Finally, extensive experimental results over four well-known tracking benchmarks indicate that the proposed AMRCF tracker achieved comparable tracking performance to most state-of-the-art (SOTA) trackers. |
| first_indexed | 2024-03-06T13:13:23Z |
| format | Article |
| id | UMPir40157 |
| institution | Universiti Malaysia Pahang |
| language | English |
| last_indexed | 2024-03-06T13:13:23Z |
| publishDate | 2022 |
| publisher | MDPI |
| record_format | dspace |
| spelling | UMPir401572024-02-07T07:19:52Z http://umpir.ump.edu.my/id/eprint/40157/ Learning augmented memory joint aberrance repressed correlation filters for visual tracking Ji, Yuanfa He, Jianzhong Sun, Xiyan Bai, Yang Wei, Zhaochuan Kamarul Hawari, Ghazali T Technology (General) TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering With its outstanding performance and tracking speed, discriminative correlation filters (DCF) have gained much attention in visual object tracking, where time-consuming correlation operations can be efficiently computed utilizing the discrete Fourier transform (DFT) with symmetric properties. Nevertheless, the inherent issues of boundary effects and filter degradation, as well as occlusion and background clutter, degrade the tracking performance. In this work, we proposed an augmented memory joint aberrance repressed correlation filter (AMRCF) for visual tracking. Based on the background-aware correlation filter (BACF), we introduced adaptive spatial regularity to mitigate the boundary effect. Several historical views and the current view are exploited to train the model together as a way to reinforce the memory. Furthermore, aberrance repression regularization was introduced to suppress response anomalies due to occlusion and deformation, while adopting the dynamic updating strategy to reduce the impact of anomalies on the appearance model. Finally, extensive experimental results over four well-known tracking benchmarks indicate that the proposed AMRCF tracker achieved comparable tracking performance to most state-of-the-art (SOTA) trackers. MDPI 2022-08 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/40157/1/Learning%20augmented%20memory%20joint%20aberrance%20repressed%20correlation.pdf Ji, Yuanfa and He, Jianzhong and Sun, Xiyan and Bai, Yang and Wei, Zhaochuan and Kamarul Hawari, Ghazali (2022) Learning augmented memory joint aberrance repressed correlation filters for visual tracking. Symmetry, 14 (1502). pp. 1-19. ISSN 2073-8994. (Published) https://doi.org/10.3390/sym14081502 https://doi.org/10.3390/sym14081502 |
| spellingShingle | T Technology (General) TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering Ji, Yuanfa He, Jianzhong Sun, Xiyan Bai, Yang Wei, Zhaochuan Kamarul Hawari, Ghazali Learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| title | Learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| title_full | Learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| title_fullStr | Learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| title_full_unstemmed | Learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| title_short | Learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| title_sort | learning augmented memory joint aberrance repressed correlation filters for visual tracking |
| topic | T Technology (General) TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering |
| url | http://umpir.ump.edu.my/id/eprint/40157/1/Learning%20augmented%20memory%20joint%20aberrance%20repressed%20correlation.pdf |
| work_keys_str_mv | AT jiyuanfa learningaugmentedmemoryjointaberrancerepressedcorrelationfiltersforvisualtracking AT hejianzhong learningaugmentedmemoryjointaberrancerepressedcorrelationfiltersforvisualtracking AT sunxiyan learningaugmentedmemoryjointaberrancerepressedcorrelationfiltersforvisualtracking AT baiyang learningaugmentedmemoryjointaberrancerepressedcorrelationfiltersforvisualtracking AT weizhaochuan learningaugmentedmemoryjointaberrancerepressedcorrelationfiltersforvisualtracking AT kamarulhawarighazali learningaugmentedmemoryjointaberrancerepressedcorrelationfiltersforvisualtracking |